← BACK_TO_LOG

Cursor Adds Auto-Review Run Mode

2026-06-03 · cursor

Cursor’s latest changelog entry is about letting agents work longer with less operator friction. Auto-review sits between strict approval gating and unchecked execution, which is the right shape for more autonomous coding loops. The release is notable because it applies to the core toolchain Cursor agents actually use, not just a cosmetic workflow setting.

Key Features or Updates

Auto-review applies to Shell, MCP, and Fetch calls. Allowlisted actions run immediately, sandboxable actions stay in the sandbox, and everything else is routed to a classifier subagent that can approve, redirect, or ask for human input.

Impact on Developers

This should cut approval fatigue for long-running agent sessions while keeping a review layer in place. It is a practical step toward more continuous agent work, especially for developers who are comfortable with policy but do not want constant interruptions.

How to use it

Turn it on in Cursor Settings under Agents > Run Mode, then add custom instructions if you want to shape how the classifier behaves. Use it first on tasks with clear boundaries, like refactors, test runs, and repository-scoped maintenance.

Read Original Post →